move to self host

1 files changed, 1098 insertions, 0 deletions

diff --git a/VRCSDK3Worlds/Assets/Editor/x64/Bakery/lmAOdir.ptx b/VRCSDK3Worlds/Assets/Editor/x64/Bakery/lmAOdir.ptx
new file mode 100644
index 00000000..edb76b28
--- /dev/null
+++ b/VRCSDK3Worlds/Assets/Editor/x64/Bakery/lmAOdir.ptx
@@ -0,0 +1,1098 @@
+//
+// Generated by NVIDIA NVVM Compiler
+//
+// Compiler Build ID: CL-23083092
+// Cuda compilation tools, release 9.1, V9.1.85
+// Based on LLVM 3.4svn
+//
+
+.version 6.1
+.target sm_30
+.address_size 64
+
+	// .globl	_Z6oxMainv
+.global .align 8 .b8 pixelID[8];
+.global .align 8 .b8 resolution[8];
+.global .align 4 .b8 normal[12];
+.global .align 4 .b8 camPos[12];
+.global .align 4 .b8 root[4];
+.global .align 4 .u32 imageEnabled;
+.global .texref lightmap;
+.global .align 16 .b8 tileInfo[16];
+.global .align 4 .u32 additive;
+.global .align 1 .b8 image_Mask[1];
+.global .align 1 .b8 image_HDR[1];
+.global .align 1 .b8 image_HDR2[1];
+.global .align 1 .b8 image_Dir[1];
+.global .align 1 .b8 uvpos[1];
+.global .align 1 .b8 uvnormal[1];
+.global .align 1 .b8 rnd_seeds[1];
+.global .align 4 .u32 samples;
+.global .align 4 .f32 lightRadius;
+.global .align 4 .f32 intensity;
+.global .align 4 .b8 _ZN21rti_internal_typeinfo7pixelIDE[8] = {82, 97, 121, 0, 8, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo10resolutionE[8] = {82, 97, 121, 0, 8, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo6normalE[8] = {82, 97, 121, 0, 12, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo6camPosE[8] = {82, 97, 121, 0, 12, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo4rootE[8] = {82, 97, 121, 0, 4, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo12imageEnabledE[8] = {82, 97, 121, 0, 4, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo8tileInfoE[8] = {82, 97, 121, 0, 16, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo8additiveE[8] = {82, 97, 121, 0, 4, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo7samplesE[8] = {82, 97, 121, 0, 4, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo11lightRadiusE[8] = {82, 97, 121, 0, 4, 0, 0, 0};
+.global .align 4 .b8 _ZN21rti_internal_typeinfo9intensityE[8] = {82, 97, 121, 0, 4, 0, 0, 0};
+.global .align 8 .u64 _ZN21rti_internal_register20reg_bitness_detectorE;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail0E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail1E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail2E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail3E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail4E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail5E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail6E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail7E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail8E;
+.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail9E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail0E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail1E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail2E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail3E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail4E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail5E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail6E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail7E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail8E;
+.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail9E;
+.global .align 4 .u32 _ZN21rti_internal_register14reg_rayIndex_xE;
+.global .align 4 .u32 _ZN21rti_internal_register14reg_rayIndex_yE;
+.global .align 4 .u32 _ZN21rti_internal_register14reg_rayIndex_zE;
+.global .align 8 .b8 _ZN21rti_internal_typename7pixelIDE[6] = {117, 105, 110, 116, 50, 0};
+.global .align 8 .b8 _ZN21rti_internal_typename10resolutionE[6] = {117, 105, 110, 116, 50, 0};
+.global .align 8 .b8 _ZN21rti_internal_typename6normalE[7] = {102, 108, 111, 97, 116, 51, 0};
+.global .align 8 .b8 _ZN21rti_internal_typename6camPosE[7] = {102, 108, 111, 97, 116, 51, 0};
+.global .align 16 .b8 _ZN21rti_internal_typename4rootE[9] = {114, 116, 79, 98, 106, 101, 99, 116, 0};
+.global .align 4 .b8 _ZN21rti_internal_typename12imageEnabledE[4] = {105, 110, 116, 0};
+.global .align 8 .b8 _ZN21rti_internal_typename8tileInfoE[6] = {117, 105, 110, 116, 52, 0};
+.global .align 4 .b8 _ZN21rti_internal_typename8additiveE[4] = {105, 110, 116, 0};
+.global .align 4 .b8 _ZN21rti_internal_typename7samplesE[4] = {105, 110, 116, 0};
+.global .align 8 .b8 _ZN21rti_internal_typename11lightRadiusE[6] = {102, 108, 111, 97, 116, 0};
+.global .align 8 .b8 _ZN21rti_internal_typename9intensityE[6] = {102, 108, 111, 97, 116, 0};
+.global .align 4 .u32 _ZN21rti_internal_typeenum7pixelIDE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum10resolutionE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum6normalE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum6camPosE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum4rootE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum12imageEnabledE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum8tileInfoE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum8additiveE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum7samplesE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum11lightRadiusE = 4919;
+.global .align 4 .u32 _ZN21rti_internal_typeenum9intensityE = 4919;
+.global .align 16 .b8 _ZN21rti_internal_semantic7pixelIDE[14] = {114, 116, 76, 97, 117, 110, 99, 104, 73, 110, 100, 101, 120, 0};
+.global .align 16 .b8 _ZN21rti_internal_semantic10resolutionE[12] = {114, 116, 76, 97, 117, 110, 99, 104, 68, 105, 109, 0};
+.global .align 16 .b8 _ZN21rti_internal_semantic6normalE[17] = {97, 116, 116, 114, 105, 98, 117, 116, 101, 32, 110, 111, 114, 109, 97, 108, 0};
+.global .align 1 .b8 _ZN21rti_internal_semantic6camPosE[1];
+.global .align 1 .b8 _ZN21rti_internal_semantic4rootE[1];
+.global .align 1 .b8 _ZN21rti_internal_semantic12imageEnabledE[1];
+.global .align 1 .b8 _ZN21rti_internal_semantic8tileInfoE[1];
+.global .align 1 .b8 _ZN21rti_internal_semantic8additiveE[1];
+.global .align 1 .b8 _ZN21rti_internal_semantic7samplesE[1];
+.global .align 1 .b8 _ZN21rti_internal_semantic11lightRadiusE[1];
+.global .align 1 .b8 _ZN21rti_internal_semantic9intensityE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation7pixelIDE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation10resolutionE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation6normalE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation6camPosE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation4rootE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation12imageEnabledE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation8tileInfoE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation8additiveE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation7samplesE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation11lightRadiusE[1];
+.global .align 1 .b8 _ZN23rti_internal_annotation9intensityE[1];
+.const .align 4 .b8 __cudart_i2opi_f[24] = {65, 144, 67, 60, 153, 149, 98, 219, 192, 221, 52, 245, 209, 87, 39, 252, 41, 21, 68, 78, 110, 131, 249, 162};
+
+.visible .entry _Z6oxMainv(
+
+)
+{
+	.local .align 4 .b8 	__local_depot0[32];
+	.reg .b64 	%SP;
+	.reg .b64 	%SPL;
+	.reg .pred 	%p<63>;
+	.reg .b16 	%rs<48>;
+	.reg .f32 	%f<392>;
+	.reg .b32 	%r<294>;
+	.reg .b64 	%rd<126>;
+
+
+	mov.u64 	%rd125, __local_depot0;
+	cvta.local.u64 	%SP, %rd125;
+	ld.global.v2.u32 	{%r97, %r98}, [pixelID];
+	cvt.u64.u32	%rd22, %r97;
+	cvt.u64.u32	%rd23, %r98;
+	mov.u64 	%rd26, uvnormal;
+	cvta.global.u64 	%rd21, %rd26;
+	mov.u32 	%r95, 2;
+	mov.u32 	%r96, 4;
+	mov.u64 	%rd25, 0;
+	// inline asm
+	call (%rd20), _rt_buffer_get_64, (%rd21, %r95, %r96, %rd22, %rd23, %rd25, %rd25);
+	// inline asm
+	ld.u32 	%r1, [%rd20];
+	shr.u32 	%r101, %r1, 16;
+	cvt.u16.u32	%rs1, %r101;
+	and.b16  	%rs3, %rs1, 255;
+	cvt.u16.u32	%rs4, %r1;
+	or.b16  	%rs5, %rs4, %rs3;
+	setp.eq.s16	%p2, %rs5, 0;
+	mov.f32 	%f358, 0f00000000;
+	mov.f32 	%f359, %f358;
+	mov.f32 	%f360, %f358;
+	@%p2 bra 	BB0_2;
+
+	ld.u8 	%rs6, [%rd20+1];
+	and.b16  	%rs8, %rs4, 255;
+	cvt.rn.f32.u16	%f96, %rs8;
+	div.rn.f32 	%f97, %f96, 0f437F0000;
+	fma.rn.f32 	%f98, %f97, 0f40000000, 0fBF800000;
+	cvt.rn.f32.u16	%f99, %rs6;
+	div.rn.f32 	%f100, %f99, 0f437F0000;
+	fma.rn.f32 	%f101, %f100, 0f40000000, 0fBF800000;
+	cvt.rn.f32.u16	%f102, %rs3;
+	div.rn.f32 	%f103, %f102, 0f437F0000;
+	fma.rn.f32 	%f104, %f103, 0f40000000, 0fBF800000;
+	mul.f32 	%f105, %f101, %f101;
+	fma.rn.f32 	%f106, %f98, %f98, %f105;
+	fma.rn.f32 	%f107, %f104, %f104, %f106;
+	sqrt.rn.f32 	%f108, %f107;
+	rcp.rn.f32 	%f109, %f108;
+	mul.f32 	%f358, %f98, %f109;
+	mul.f32 	%f359, %f101, %f109;
+	mul.f32 	%f360, %f104, %f109;
+
+BB0_2:
+	ld.global.v2.u32 	{%r102, %r103}, [pixelID];
+	ld.global.v2.u32 	{%r105, %r106}, [tileInfo];
+	add.s32 	%r2, %r102, %r105;
+	add.s32 	%r3, %r103, %r106;
+	setp.eq.f32	%p3, %f359, 0f00000000;
+	setp.eq.f32	%p4, %f358, 0f00000000;
+	and.pred  	%p5, %p4, %p3;
+	setp.eq.f32	%p6, %f360, 0f00000000;
+	and.pred  	%p7, %p5, %p6;
+	@%p7 bra 	BB0_75;
+	bra.uni 	BB0_3;
+
+BB0_75:
+	ld.global.u8 	%rs30, [imageEnabled];
+	and.b16  	%rs31, %rs30, 4;
+	setp.eq.s16	%p59, %rs31, 0;
+	@%p59 bra 	BB0_79;
+
+	ld.global.u32 	%r250, [additive];
+	setp.eq.s32	%p60, %r250, 0;
+	cvt.u64.u32	%rd18, %r2;
+	cvt.u64.u32	%rd19, %r3;
+	@%p60 bra 	BB0_78;
+
+	mov.u64 	%rd99, image_HDR;
+	cvta.global.u64 	%rd88, %rd99;
+	mov.u32 	%r254, 8;
+	// inline asm
+	call (%rd87), _rt_buffer_get_64, (%rd88, %r95, %r254, %rd18, %rd19, %rd25, %rd25);
+	// inline asm
+	ld.v4.u16 	{%rs38, %rs39, %rs40, %rs41}, [%rd87];
+	// inline asm
+	{  cvt.f32.f16 %f348, %rs38;}
+
+	// inline asm
+	// inline asm
+	{  cvt.f32.f16 %f349, %rs39;}
+
+	// inline asm
+	// inline asm
+	{  cvt.f32.f16 %f350, %rs40;}
+
+	// inline asm
+	// inline asm
+	call (%rd93), _rt_buffer_get_64, (%rd88, %r95, %r254, %rd18, %rd19, %rd25, %rd25);
+	// inline asm
+	add.f32 	%f351, %f348, 0f00000000;
+	add.f32 	%f352, %f349, 0f00000000;
+	add.f32 	%f353, %f350, 0f00000000;
+	// inline asm
+	{  cvt.rn.f16.f32 %rs37, %f353;}
+
+	// inline asm
+	// inline asm
+	{  cvt.rn.f16.f32 %rs36, %f352;}
+
+	// inline asm
+	// inline asm
+	{  cvt.rn.f16.f32 %rs35, %f351;}
+
+	// inline asm
+	mov.u16 	%rs42, 0;
+	st.v4.u16 	[%rd93], {%rs35, %rs36, %rs37, %rs42};
+	bra.uni 	BB0_79;
+
+BB0_3:
+	ld.global.v2.u32 	{%r114, %r115}, [pixelID];
+	cvt.u64.u32	%rd29, %r114;
+	cvt.u64.u32	%rd30, %r115;
+	mov.u64 	%rd39, uvpos;
+	cvta.global.u64 	%rd28, %rd39;
+	mov.u32 	%r111, 12;
+	// inline asm
+	call (%rd27), _rt_buffer_get_64, (%rd28, %r95, %r111, %rd29, %rd30, %rd25, %rd25);
+	// inline asm
+	ld.f32 	%f114, [%rd27+8];
+	ld.f32 	%f115, [%rd27+4];
+	ld.f32 	%f116, [%rd27];
+	mul.f32 	%f117, %f116, 0f3456BF95;
+	mul.f32 	%f118, %f115, 0f3456BF95;
+	mul.f32 	%f119, %f114, 0f3456BF95;
+	abs.f32 	%f120, %f358;
+	div.rn.f32 	%f121, %f117, %f120;
+	abs.f32 	%f122, %f359;
+	div.rn.f32 	%f123, %f118, %f122;
+	abs.f32 	%f124, %f360;
+	div.rn.f32 	%f125, %f119, %f124;
+	abs.f32 	%f126, %f121;
+	abs.f32 	%f127, %f123;
+	abs.f32 	%f128, %f125;
+	mov.f32 	%f129, 0f38D1B717;
+	max.f32 	%f130, %f126, %f129;
+	max.f32 	%f131, %f127, %f129;
+	max.f32 	%f132, %f128, %f129;
+	fma.rn.f32 	%f7, %f358, %f130, %f116;
+	fma.rn.f32 	%f8, %f359, %f131, %f115;
+	fma.rn.f32 	%f9, %f360, %f132, %f114;
+	setp.gt.f32	%p8, %f120, %f124;
+	neg.f32 	%f133, %f359;
+	selp.f32	%f134, %f133, 0f00000000, %p8;
+	neg.f32 	%f135, %f360;
+	selp.f32	%f136, %f358, %f135, %p8;
+	selp.f32	%f137, 0f00000000, %f359, %p8;
+	mul.f32 	%f138, %f136, %f136;
+	fma.rn.f32 	%f139, %f134, %f134, %f138;
+	fma.rn.f32 	%f140, %f137, %f137, %f139;
+	sqrt.rn.f32 	%f141, %f140;
+	rcp.rn.f32 	%f142, %f141;
+	mul.f32 	%f10, %f134, %f142;
+	mul.f32 	%f11, %f136, %f142;
+	mul.f32 	%f12, %f137, %f142;
+	ld.global.v2.u32 	{%r118, %r119}, [pixelID];
+	cvt.u64.u32	%rd35, %r118;
+	cvt.u64.u32	%rd36, %r119;
+	mov.u64 	%rd40, rnd_seeds;
+	cvta.global.u64 	%rd34, %rd40;
+	// inline asm
+	call (%rd33), _rt_buffer_get_64, (%rd34, %r95, %r96, %rd35, %rd36, %rd25, %rd25);
+	// inline asm
+	ld.global.u32 	%r264, [samples];
+	mov.f32 	%f381, 0f00000000;
+	setp.lt.s32	%p9, %r264, 1;
+	@%p9 bra 	BB0_4;
+
+	cvt.rn.f32.s32	%f147, %r264;
+	rcp.rn.f32 	%f13, %f147;
+	ld.u32 	%r290, [%rd33];
+	mul.f32 	%f14, %f7, 0f3456BF95;
+	mul.f32 	%f15, %f8, 0f3456BF95;
+	mul.f32 	%f16, %f9, 0f3456BF95;
+	mul.f32 	%f148, %f358, %f11;
+	mul.f32 	%f149, %f359, %f10;
+	sub.f32 	%f17, %f149, %f148;
+	mul.f32 	%f150, %f360, %f10;
+	mul.f32 	%f151, %f358, %f12;
+	sub.f32 	%f18, %f151, %f150;
+	mul.f32 	%f152, %f359, %f12;
+	mul.f32 	%f153, %f360, %f11;
+	sub.f32 	%f19, %f153, %f152;
+	mov.f32 	%f381, 0f00000000;
+	mov.u32 	%r265, 0;
+	abs.f32 	%f154, %f15;
+	abs.f32 	%f155, %f14;
+	max.f32 	%f156, %f155, %f154;
+	abs.f32 	%f157, %f16;
+	max.f32 	%f158, %f156, %f157;
+	mov.f32 	%f382, %f381;
+	mov.f32 	%f383, %f381;
+	mov.f32 	%f384, %f381;
+
+BB0_6:
+	setp.lt.s32	%p10, %r264, 1;
+	@%p10 bra 	BB0_55;
+
+	cvt.rn.f32.s32	%f24, %r265;
+	max.f32 	%f25, %f158, %f129;
+	mov.u32 	%r267, 0;
+
+BB0_8:
+	mad.lo.s32 	%r124, %r290, 1664525, 1013904223;
+	and.b32  	%r125, %r124, 16777215;
+	cvt.rn.f32.u32	%f160, %r125;
+	fma.rn.f32 	%f161, %f160, 0f33800000, %f24;
+	mul.f32 	%f162, %f13, %f161;
+	mad.lo.s32 	%r290, %r124, 1664525, 1013904223;
+	and.b32  	%r126, %r290, 16777215;
+	cvt.rn.f32.u32	%f163, %r126;
+	cvt.rn.f32.s32	%f164, %r267;
+	fma.rn.f32 	%f165, %f163, 0f33800000, %f164;
+	mul.f32 	%f166, %f13, %f165;
+	sqrt.rn.f32 	%f30, %f162;
+	mul.f32 	%f375, %f166, 0f40C90FDB;
+	abs.f32 	%f32, %f375;
+	setp.neu.f32	%p11, %f32, 0f7F800000;
+	mov.f32 	%f369, %f375;
+	@%p11 bra 	BB0_10;
+
+	mov.f32 	%f167, 0f00000000;
+	mul.rn.f32 	%f369, %f375, %f167;
+
+BB0_10:
+	mul.f32 	%f168, %f369, 0f3F22F983;
+	cvt.rni.s32.f32	%r278, %f168;
+	cvt.rn.f32.s32	%f169, %r278;
+	neg.f32 	%f170, %f169;
+	mov.f32 	%f171, 0f3FC90FDA;
+	fma.rn.f32 	%f172, %f170, %f171, %f369;
+	mov.f32 	%f173, 0f33A22168;
+	fma.rn.f32 	%f174, %f170, %f173, %f172;
+	mov.f32 	%f175, 0f27C234C5;
+	fma.rn.f32 	%f370, %f170, %f175, %f174;
+	abs.f32 	%f176, %f369;
+	setp.leu.f32	%p12, %f176, 0f47CE4780;
+	@%p12 bra 	BB0_21;
+
+	mov.b32 	 %r13, %f369;
+	shr.u32 	%r14, %r13, 23;
+	shl.b32 	%r129, %r13, 8;
+	or.b32  	%r15, %r129, -2147483648;
+	add.u64 	%rd42, %SP, 4;
+	cvta.to.local.u64 	%rd122, %rd42;
+	mov.u32 	%r270, 0;
+	mov.u64 	%rd121, __cudart_i2opi_f;
+	mov.u32 	%r269, -6;
+
+BB0_12:
+	.pragma "nounroll";
+	ld.const.u32 	%r132, [%rd121];
+	// inline asm
+	{
+	mad.lo.cc.u32   %r130, %r132, %r15, %r270;
+	madc.hi.u32     %r270, %r132, %r15,  0;
+	}
+	// inline asm
+	st.local.u32 	[%rd122], %r130;
+	add.s64 	%rd122, %rd122, 4;
+	add.s64 	%rd121, %rd121, 4;
+	add.s32 	%r269, %r269, 1;
+	setp.ne.s32	%p13, %r269, 0;
+	@%p13 bra 	BB0_12;
+
+	and.b32  	%r135, %r14, 255;
+	add.s32 	%r136, %r135, -128;
+	shr.u32 	%r137, %r136, 5;
+	and.b32  	%r20, %r13, -2147483648;
+	cvta.to.local.u64 	%rd44, %rd42;
+	st.local.u32 	[%rd44+24], %r270;
+	mov.u32 	%r138, 6;
+	sub.s32 	%r139, %r138, %r137;
+	mul.wide.s32 	%rd45, %r139, 4;
+	add.s64 	%rd8, %rd44, %rd45;
+	ld.local.u32 	%r271, [%rd8];
+	ld.local.u32 	%r272, [%rd8+-4];
+	and.b32  	%r23, %r14, 31;
+	setp.eq.s32	%p14, %r23, 0;
+	@%p14 bra 	BB0_15;
+
+	mov.u32 	%r140, 32;
+	sub.s32 	%r141, %r140, %r23;
+	shr.u32 	%r142, %r272, %r141;
+	shl.b32 	%r143, %r271, %r23;
+	add.s32 	%r271, %r142, %r143;
+	ld.local.u32 	%r144, [%rd8+-8];
+	shr.u32 	%r145, %r144, %r141;
+	shl.b32 	%r146, %r272, %r23;
+	add.s32 	%r272, %r145, %r146;
+
+BB0_15:
+	shr.u32 	%r147, %r272, 30;
+	shl.b32 	%r148, %r271, 2;
+	add.s32 	%r273, %r147, %r148;
+	shl.b32 	%r29, %r272, 2;
+	shr.u32 	%r149, %r273, 31;
+	shr.u32 	%r150, %r271, 30;
+	add.s32 	%r30, %r149, %r150;
+	setp.eq.s32	%p15, %r149, 0;
+	@%p15 bra 	BB0_16;
+	bra.uni 	BB0_17;
+
+BB0_16:
+	mov.u32 	%r274, %r20;
+	mov.u32 	%r275, %r29;
+	bra.uni 	BB0_18;
+
+BB0_17:
+	not.b32 	%r151, %r273;
+	neg.s32 	%r275, %r29;
+	setp.eq.s32	%p16, %r29, 0;
+	selp.u32	%r152, 1, 0, %p16;
+	add.s32 	%r273, %r152, %r151;
+	xor.b32  	%r274, %r20, -2147483648;
+
+BB0_18:
+	clz.b32 	%r277, %r273;
+	setp.eq.s32	%p17, %r277, 0;
+	shl.b32 	%r153, %r273, %r277;
+	mov.u32 	%r154, 32;
+	sub.s32 	%r155, %r154, %r277;
+	shr.u32 	%r156, %r275, %r155;
+	add.s32 	%r157, %r156, %r153;
+	selp.b32	%r38, %r273, %r157, %p17;
+	mov.u32 	%r158, -921707870;
+	mul.hi.u32 	%r276, %r38, %r158;
+	setp.eq.s32	%p18, %r20, 0;
+	neg.s32 	%r159, %r30;
+	selp.b32	%r278, %r30, %r159, %p18;
+	setp.lt.s32	%p19, %r276, 1;
+	@%p19 bra 	BB0_20;
+
+	mul.lo.s32 	%r160, %r38, -921707870;
+	shr.u32 	%r161, %r160, 31;
+	shl.b32 	%r162, %r276, 1;
+	add.s32 	%r276, %r161, %r162;
+	add.s32 	%r277, %r277, 1;
+
+BB0_20:
+	mov.u32 	%r163, 126;
+	sub.s32 	%r164, %r163, %r277;
+	shl.b32 	%r165, %r164, 23;
+	add.s32 	%r166, %r276, 1;
+	shr.u32 	%r167, %r166, 7;
+	add.s32 	%r168, %r167, 1;
+	shr.u32 	%r169, %r168, 1;
+	add.s32 	%r170, %r169, %r165;
+	or.b32  	%r171, %r170, %r274;
+	mov.b32 	 %f370, %r171;
+
+BB0_21:
+	mul.rn.f32 	%f38, %f370, %f370;
+	add.s32 	%r46, %r278, 1;
+	and.b32  	%r47, %r46, 1;
+	setp.eq.s32	%p20, %r47, 0;
+	@%p20 bra 	BB0_23;
+	bra.uni 	BB0_22;
+
+BB0_23:
+	mov.f32 	%f179, 0f3C08839E;
+	mov.f32 	%f180, 0fB94CA1F9;
+	fma.rn.f32 	%f371, %f180, %f38, %f179;
+	bra.uni 	BB0_24;
+
+BB0_22:
+	mov.f32 	%f177, 0fBAB6061A;
+	mov.f32 	%f178, 0f37CCF5CE;
+	fma.rn.f32 	%f371, %f178, %f38, %f177;
+
+BB0_24:
+	@%p20 bra 	BB0_26;
+	bra.uni 	BB0_25;
+
+BB0_26:
+	mov.f32 	%f184, 0fBE2AAAA3;
+	fma.rn.f32 	%f185, %f371, %f38, %f184;
+	mov.f32 	%f186, 0f00000000;
+	fma.rn.f32 	%f372, %f185, %f38, %f186;
+	bra.uni 	BB0_27;
+
+BB0_25:
+	mov.f32 	%f181, 0f3D2AAAA5;
+	fma.rn.f32 	%f182, %f371, %f38, %f181;
+	mov.f32 	%f183, 0fBF000000;
+	fma.rn.f32 	%f372, %f182, %f38, %f183;
+
+BB0_27:
+	fma.rn.f32 	%f373, %f372, %f370, %f370;
+	@%p20 bra 	BB0_29;
+
+	mov.f32 	%f187, 0f3F800000;
+	fma.rn.f32 	%f373, %f372, %f38, %f187;
+
+BB0_29:
+	and.b32  	%r172, %r46, 2;
+	setp.eq.s32	%p23, %r172, 0;
+	@%p23 bra 	BB0_31;
+
+	mov.f32 	%f188, 0f00000000;
+	mov.f32 	%f189, 0fBF800000;
+	fma.rn.f32 	%f373, %f373, %f189, %f188;
+
+BB0_31:
+	@%p11 bra 	BB0_33;
+
+	mov.f32 	%f190, 0f00000000;
+	mul.rn.f32 	%f375, %f375, %f190;
+
+BB0_33:
+	mul.f32 	%f191, %f375, 0f3F22F983;
+	cvt.rni.s32.f32	%r288, %f191;
+	cvt.rn.f32.s32	%f192, %r288;
+	neg.f32 	%f193, %f192;
+	fma.rn.f32 	%f195, %f193, %f171, %f375;
+	fma.rn.f32 	%f197, %f193, %f173, %f195;
+	fma.rn.f32 	%f376, %f193, %f175, %f197;
+	abs.f32 	%f199, %f375;
+	setp.leu.f32	%p25, %f199, 0f47CE4780;
+	@%p25 bra 	BB0_44;
+
+	mov.b32 	 %r49, %f375;
+	shr.u32 	%r50, %r49, 23;
+	shl.b32 	%r175, %r49, 8;
+	or.b32  	%r51, %r175, -2147483648;
+	add.u64 	%rd47, %SP, 4;
+	cvta.to.local.u64 	%rd124, %rd47;
+	mov.u32 	%r280, 0;
+	mov.u64 	%rd123, __cudart_i2opi_f;
+	mov.u32 	%r279, -6;
+
+BB0_35:
+	.pragma "nounroll";
+	ld.const.u32 	%r178, [%rd123];
+	// inline asm
+	{
+	mad.lo.cc.u32   %r176, %r178, %r51, %r280;
+	madc.hi.u32     %r280, %r178, %r51,  0;
+	}
+	// inline asm
+	st.local.u32 	[%rd124], %r176;
+	add.s64 	%rd124, %rd124, 4;
+	add.s64 	%rd123, %rd123, 4;
+	add.s32 	%r279, %r279, 1;
+	setp.ne.s32	%p26, %r279, 0;
+	@%p26 bra 	BB0_35;
+
+	and.b32  	%r181, %r50, 255;
+	add.s32 	%r182, %r181, -128;
+	shr.u32 	%r183, %r182, 5;
+	and.b32  	%r56, %r49, -2147483648;
+	cvta.to.local.u64 	%rd49, %rd47;
+	st.local.u32 	[%rd49+24], %r280;
+	mov.u32 	%r184, 6;
+	sub.s32 	%r185, %r184, %r183;
+	mul.wide.s32 	%rd50, %r185, 4;
+	add.s64 	%rd14, %rd49, %rd50;
+	ld.local.u32 	%r281, [%rd14];
+	ld.local.u32 	%r282, [%rd14+-4];
+	and.b32  	%r59, %r50, 31;
+	setp.eq.s32	%p27, %r59, 0;
+	@%p27 bra 	BB0_38;
+
+	mov.u32 	%r186, 32;
+	sub.s32 	%r187, %r186, %r59;
+	shr.u32 	%r188, %r282, %r187;
+	shl.b32 	%r189, %r281, %r59;
+	add.s32 	%r281, %r188, %r189;
+	ld.local.u32 	%r190, [%rd14+-8];
+	shr.u32 	%r191, %r190, %r187;
+	shl.b32 	%r192, %r282, %r59;
+	add.s32 	%r282, %r191, %r192;
+
+BB0_38:
+	shr.u32 	%r193, %r282, 30;
+	shl.b32 	%r194, %r281, 2;
+	add.s32 	%r283, %r193, %r194;
+	shl.b32 	%r65, %r282, 2;
+	shr.u32 	%r195, %r283, 31;
+	shr.u32 	%r196, %r281, 30;
+	add.s32 	%r66, %r195, %r196;
+	setp.eq.s32	%p28, %r195, 0;
+	@%p28 bra 	BB0_39;
+	bra.uni 	BB0_40;
+
+BB0_39:
+	mov.u32 	%r284, %r56;
+	mov.u32 	%r285, %r65;
+	bra.uni 	BB0_41;
+
+BB0_40:
+	not.b32 	%r197, %r283;
+	neg.s32 	%r285, %r65;
+	setp.eq.s32	%p29, %r65, 0;
+	selp.u32	%r198, 1, 0, %p29;
+	add.s32 	%r283, %r198, %r197;
+	xor.b32  	%r284, %r56, -2147483648;
+
+BB0_41:
+	clz.b32 	%r287, %r283;
+	setp.eq.s32	%p30, %r287, 0;
+	shl.b32 	%r199, %r283, %r287;
+	mov.u32 	%r200, 32;
+	sub.s32 	%r201, %r200, %r287;
+	shr.u32 	%r202, %r285, %r201;
+	add.s32 	%r203, %r202, %r199;
+	selp.b32	%r74, %r283, %r203, %p30;
+	mov.u32 	%r204, -921707870;
+	mul.hi.u32 	%r286, %r74, %r204;
+	setp.eq.s32	%p31, %r56, 0;
+	neg.s32 	%r205, %r66;
+	selp.b32	%r288, %r66, %r205, %p31;
+	setp.lt.s32	%p32, %r286, 1;
+	@%p32 bra 	BB0_43;
+
+	mul.lo.s32 	%r206, %r74, -921707870;
+	shr.u32 	%r207, %r206, 31;
+	shl.b32 	%r208, %r286, 1;
+	add.s32 	%r286, %r207, %r208;
+	add.s32 	%r287, %r287, 1;
+
+BB0_43:
+	mov.u32 	%r209, 126;
+	sub.s32 	%r210, %r209, %r287;
+	shl.b32 	%r211, %r210, 23;
+	add.s32 	%r212, %r286, 1;
+	shr.u32 	%r213, %r212, 7;
+	add.s32 	%r214, %r213, 1;
+	shr.u32 	%r215, %r214, 1;
+	add.s32 	%r216, %r215, %r211;
+	or.b32  	%r217, %r216, %r284;
+	mov.b32 	 %f376, %r217;
+
+BB0_44:
+	mul.rn.f32 	%f55, %f376, %f376;
+	and.b32  	%r82, %r288, 1;
+	setp.eq.s32	%p33, %r82, 0;
+	@%p33 bra 	BB0_46;
+	bra.uni 	BB0_45;
+
+BB0_46:
+	mov.f32 	%f202, 0f3C08839E;
+	mov.f32 	%f203, 0fB94CA1F9;
+	fma.rn.f32 	%f377, %f203, %f55, %f202;
+	bra.uni 	BB0_47;
+
+BB0_45:
+	mov.f32 	%f200, 0fBAB6061A;
+	mov.f32 	%f201, 0f37CCF5CE;
+	fma.rn.f32 	%f377, %f201, %f55, %f200;
+
+BB0_47:
+	@%p33 bra 	BB0_49;
+	bra.uni 	BB0_48;
+
+BB0_49:
+	mov.f32 	%f207, 0fBE2AAAA3;
+	fma.rn.f32 	%f208, %f377, %f55, %f207;
+	mov.f32 	%f209, 0f00000000;
+	fma.rn.f32 	%f378, %f208, %f55, %f209;
+	bra.uni 	BB0_50;
+
+BB0_48:
+	mov.f32 	%f204, 0f3D2AAAA5;
+	fma.rn.f32 	%f205, %f377, %f55, %f204;
+	mov.f32 	%f206, 0fBF000000;
+	fma.rn.f32 	%f378, %f205, %f55, %f206;
+
+BB0_50:
+	fma.rn.f32 	%f379, %f378, %f376, %f376;
+	@%p33 bra 	BB0_52;
+
+	mov.f32 	%f210, 0f3F800000;
+	fma.rn.f32 	%f379, %f378, %f55, %f210;
+
+BB0_52:
+	and.b32  	%r218, %r288, 2;
+	setp.eq.s32	%p36, %r218, 0;
+	@%p36 bra 	BB0_54;
+
+	mov.f32 	%f211, 0f00000000;
+	mov.f32 	%f212, 0fBF800000;
+	fma.rn.f32 	%f379, %f379, %f212, %f211;
+
+BB0_54:
+	mul.f32 	%f221, %f30, %f373;
+	add.u64 	%rd51, %SP, 0;
+	cvta.to.local.u64 	%rd52, %rd51;
+	mul.f32 	%f222, %f221, %f221;
+	mov.f32 	%f223, 0f3F800000;
+	sub.f32 	%f224, %f223, %f222;
+	mul.f32 	%f225, %f30, %f379;
+	mul.f32 	%f226, %f225, %f225;
+	sub.f32 	%f227, %f224, %f226;
+	mov.f32 	%f228, 0f00000000;
+	max.f32 	%f229, %f228, %f227;
+	sqrt.rn.f32 	%f230, %f229;
+	mul.f32 	%f231, %f10, %f225;
+	mul.f32 	%f232, %f11, %f225;
+	mul.f32 	%f233, %f12, %f225;
+	fma.rn.f32 	%f234, %f19, %f221, %f231;
+	fma.rn.f32 	%f235, %f18, %f221, %f232;
+	fma.rn.f32 	%f236, %f17, %f221, %f233;
+	fma.rn.f32 	%f216, %f358, %f230, %f234;
+	fma.rn.f32 	%f217, %f359, %f230, %f235;
+	fma.rn.f32 	%f218, %f360, %f230, %f236;
+	ld.global.f32 	%f220, [lightRadius];
+	mov.u32 	%r222, 1065353216;
+	st.local.u32 	[%rd52], %r222;
+	ld.global.u32 	%r219, [root];
+	mov.u32 	%r220, 1;
+	// inline asm
+	call _rt_trace_64, (%r219, %f7, %f8, %f9, %f216, %f217, %f218, %r220, %f25, %f220, %rd51, %r96);
+	// inline asm
+	ld.local.f32 	%f237, [%rd52];
+	add.f32 	%f381, %f381, %f237;
+	fma.rn.f32 	%f384, %f216, %f237, %f384;
+	fma.rn.f32 	%f383, %f217, %f237, %f383;
+	fma.rn.f32 	%f382, %f218, %f237, %f382;
+	ld.global.u32 	%r264, [samples];
+	add.s32 	%r267, %r267, 1;
+	setp.lt.s32	%p37, %r267, %r264;
+	@%p37 bra 	BB0_8;
+
+BB0_55:
+	add.s32 	%r265, %r265, 1;
+	setp.lt.s32	%p38, %r265, %r264;
+	@%p38 bra 	BB0_6;
+	bra.uni 	BB0_56;
+
+BB0_4:
+	mov.f32 	%f382, %f381;
+	mov.f32 	%f383, %f381;
+	mov.f32 	%f384, %f381;
+
+BB0_56:
+	mul.lo.s32 	%r223, %r264, %r264;
+	cvt.rn.f32.s32	%f238, %r223;
+	div.rn.f32 	%f239, %f381, %f238;
+	add.f32 	%f240, %f239, 0fBF800000;
+	ld.global.f32 	%f241, [intensity];
+	fma.rn.f32 	%f242, %f241, %f240, 0f3F800000;
+	cvt.sat.f32.f32	%f79, %f242;
+	ld.global.u8 	%rs10, [imageEnabled];
+	and.b16  	%rs11, %rs10, 4;
+	setp.eq.s16	%p39, %rs11, 0;
+	@%p39 bra 	BB0_60;
+
+	ld.global.u32 	%r224, [additive];
+	setp.eq.s32	%p40, %r224, 0;
+	cvt.u64.u32	%rd15, %r2;
+	cvt.u64.u32	%rd16, %r3;
+	mov.f32 	%f243, 0f3F800000;
+	// inline asm
+	{  cvt.rn.f16.f32 %rs12, %f243;}
+
+	// inline asm
+	@%p40 bra 	BB0_59;
+
+	mov.u64 	%rd65, image_HDR;
+	cvta.global.u64 	%rd54, %rd65;
+	mov.u32 	%r228, 8;
+	// inline asm
+	call (%rd53), _rt_buffer_get_64, (%rd54, %r95, %r228, %rd15, %rd16, %rd25, %rd25);
+	// inline asm
+	ld.v4.u16 	{%rs19, %rs20, %rs21, %rs22}, [%rd53];
+	// inline asm
+	{  cvt.f32.f16 %f244, %rs19;}
+
+	// inline asm
+	// inline asm
+	{  cvt.f32.f16 %f245, %rs20;}
+
+	// inline asm
+	// inline asm
+	{  cvt.f32.f16 %f246, %rs21;}
+
+	// inline asm
+	// inline asm
+	call (%rd59), _rt_buffer_get_64, (%rd54, %r95, %r228, %rd15, %rd16, %rd25, %rd25);
+	// inline asm
+	add.f32 	%f247, %f79, %f244;
+	add.f32 	%f248, %f79, %f245;
+	add.f32 	%f249, %f79, %f246;
+	// inline asm
+	{  cvt.rn.f16.f32 %rs18, %f249;}
+
+	// inline asm
+	// inline asm
+	{  cvt.rn.f16.f32 %rs17, %f248;}
+
+	// inline asm
+	// inline asm
+	{  cvt.rn.f16.f32 %rs16, %f247;}
+
+	// inline asm
+	st.v4.u16 	[%rd59], {%rs16, %rs17, %rs18, %rs12};
+	bra.uni 	BB0_60;
+
+BB0_78:
+	mov.u64 	%rd106, image_HDR;
+	cvta.global.u64 	%rd101, %rd106;
+	mov.u32 	%r256, 8;
+	// inline asm
+	call (%rd100), _rt_buffer_get_64, (%rd101, %r95, %r256, %rd18, %rd19, %rd25, %rd25);
+	// inline asm
+	mov.f32 	%f354, 0f00000000;
+	// inline asm
+	{  cvt.rn.f16.f32 %rs43, %f354;}
+
+	// inline asm
+	mov.u16 	%rs44, 0;
+	st.v4.u16 	[%rd100], {%rs43, %rs43, %rs43, %rs44};
+
+BB0_79:
+	ld.global.u32 	%r293, [imageEnabled];
+	and.b32  	%r257, %r293, 8;
+	setp.eq.s32	%p61, %r257, 0;
+	@%p61 bra 	BB0_81;
+
+	cvt.u64.u32	%rd109, %r2;
+	cvt.u64.u32	%rd110, %r3;
+	mov.u64 	%rd113, image_Mask;
+	cvta.global.u64 	%rd108, %rd113;
+	// inline asm
+	call (%rd107), _rt_buffer_get_64, (%rd108, %r95, %r95, %rd109, %rd110, %rd25, %rd25);
+	// inline asm
+	mov.f32 	%f357, 0f00000000;
+	cvt.rzi.u32.f32	%r260, %f357;
+	cvt.u16.u32	%rs45, %r260;
+	mov.u16 	%rs46, 0;
+	st.v2.u8 	[%rd107], {%rs45, %rs46};
+	ld.global.u32 	%r293, [imageEnabled];
+
+BB0_81:
+	and.b32  	%r261, %r293, 64;
+	setp.eq.s32	%p62, %r261, 0;
+	@%p62 bra 	BB0_83;
+
+	cvt.u64.u32	%rd116, %r2;
+	cvt.u64.u32	%rd117, %r3;
+	mov.u64 	%rd120, image_Dir;
+	cvta.global.u64 	%rd115, %rd120;
+	// inline asm
+	call (%rd114), _rt_buffer_get_64, (%rd115, %r95, %r96, %rd116, %rd117, %rd25, %rd25);
+	// inline asm
+	mov.u16 	%rs47, 0;
+	st.v4.u8 	[%rd114], {%rs47, %rs47, %rs47, %rs47};
+	bra.uni 	BB0_83;
+
+BB0_59:
+	mov.u64 	%rd72, image_HDR;
+	cvta.global.u64 	%rd67, %rd72;
+	mov.u32 	%r230, 8;
+	// inline asm
+	call (%rd66), _rt_buffer_get_64, (%rd67, %r95, %r230, %rd15, %rd16, %rd25, %rd25);
+	// inline asm
+	// inline asm
+	{  cvt.rn.f16.f32 %rs23, %f79;}
+
+	// inline asm
+	st.v4.u16 	[%rd66], {%rs23, %rs23, %rs23, %rs12};
+
+BB0_60:
+	ld.global.u32 	%r292, [imageEnabled];
+	and.b32  	%r231, %r292, 8;
+	setp.eq.s32	%p41, %r231, 0;
+	@%p41 bra 	BB0_73;
+
+	cvt.u64.u32	%rd75, %r2;
+	cvt.u64.u32	%rd76, %r3;
+	mov.u64 	%rd79, image_Mask;
+	cvta.global.u64 	%rd74, %rd79;
+	// inline asm
+	call (%rd73), _rt_buffer_get_64, (%rd74, %r95, %r95, %rd75, %rd76, %rd25, %rd25);
+	// inline asm
+	mov.f32 	%f253, 0f3E68BA2E;
+	cvt.rzi.f32.f32	%f254, %f253;
+	fma.rn.f32 	%f255, %f254, 0fC0000000, 0f3EE8BA2E;
+	abs.f32 	%f80, %f255;
+	abs.f32 	%f81, %f79;
+	setp.lt.f32	%p42, %f81, 0f00800000;
+	mul.f32 	%f256, %f81, 0f4B800000;
+	selp.f32	%f257, 0fC3170000, 0fC2FE0000, %p42;
+	selp.f32	%f258, %f256, %f81, %p42;
+	mov.b32 	 %r234, %f258;
+	and.b32  	%r235, %r234, 8388607;
+	or.b32  	%r236, %r235, 1065353216;
+	mov.b32 	 %f259, %r236;
+	shr.u32 	%r237, %r234, 23;
+	cvt.rn.f32.u32	%f260, %r237;
+	add.f32 	%f261, %f257, %f260;
+	setp.gt.f32	%p43, %f259, 0f3FB504F3;
+	mul.f32 	%f262, %f259, 0f3F000000;
+	add.f32 	%f263, %f261, 0f3F800000;
+	selp.f32	%f264, %f262, %f259, %p43;
+	selp.f32	%f265, %f263, %f261, %p43;
+	add.f32 	%f266, %f264, 0fBF800000;
+	add.f32 	%f252, %f264, 0f3F800000;
+	// inline asm
+	rcp.approx.ftz.f32 %f251,%f252;
+	// inline asm
+	add.f32 	%f267, %f266, %f266;
+	mul.f32 	%f268, %f251, %f267;
+	mul.f32 	%f269, %f268, %f268;
+	mov.f32 	%f270, 0f3C4CAF63;
+	mov.f32 	%f271, 0f3B18F0FE;
+	fma.rn.f32 	%f272, %f271, %f269, %f270;
+	mov.f32 	%f273, 0f3DAAAABD;
+	fma.rn.f32 	%f274, %f272, %f269, %f273;
+	mul.rn.f32 	%f275, %f274, %f269;
+	mul.rn.f32 	%f276, %f275, %f268;
+	sub.f32 	%f277, %f266, %f268;
+	neg.f32 	%f278, %f268;
+	add.f32 	%f279, %f277, %f277;
+	fma.rn.f32 	%f280, %f278, %f266, %f279;
+	mul.rn.f32 	%f281, %f251, %f280;
+	add.f32 	%f282, %f276, %f268;
+	sub.f32 	%f283, %f268, %f282;
+	add.f32 	%f284, %f276, %f283;
+	add.f32 	%f285, %f281, %f284;
+	add.f32 	%f286, %f282, %f285;
+	sub.f32 	%f287, %f282, %f286;
+	add.f32 	%f288, %f285, %f287;
+	mov.f32 	%f289, 0f3F317200;
+	mul.rn.f32 	%f290, %f265, %f289;
+	mov.f32 	%f291, 0f35BFBE8E;
+	mul.rn.f32 	%f292, %f265, %f291;
+	add.f32 	%f293, %f290, %f286;
+	sub.f32 	%f294, %f290, %f293;
+	add.f32 	%f295, %f286, %f294;
+	add.f32 	%f296, %f288, %f295;
+	add.f32 	%f297, %f292, %f296;
+	add.f32 	%f298, %f293, %f297;
+	sub.f32 	%f299, %f293, %f298;
+	add.f32 	%f300, %f297, %f299;
+	mov.f32 	%f301, 0f3EE8BA2E;
+	mul.rn.f32 	%f302, %f301, %f298;
+	neg.f32 	%f303, %f302;
+	fma.rn.f32 	%f304, %f301, %f298, %f303;
+	fma.rn.f32 	%f305, %f301, %f300, %f304;
+	mov.f32 	%f306, 0f00000000;
+	fma.rn.f32 	%f307, %f306, %f298, %f305;
+	add.rn.f32 	%f308, %f302, %f307;
+	neg.f32 	%f309, %f308;
+	add.rn.f32 	%f310, %f302, %f309;
+	add.rn.f32 	%f311, %f310, %f307;
+	mov.b32 	 %r238, %f308;
+	setp.eq.s32	%p44, %r238, 1118925336;
+	add.s32 	%r239, %r238, -1;
+	mov.b32 	 %f312, %r239;
+	add.f32 	%f313, %f311, 0f37000000;
+	selp.f32	%f314, %f312, %f308, %p44;
+	selp.f32	%f82, %f313, %f311, %p44;
+	mul.f32 	%f315, %f314, 0f3FB8AA3B;
+	cvt.rzi.f32.f32	%f316, %f315;
+	mov.f32 	%f317, 0fBF317200;
+	fma.rn.f32 	%f318, %f316, %f317, %f314;
+	mov.f32 	%f319, 0fB5BFBE8E;
+	fma.rn.f32 	%f320, %f316, %f319, %f318;
+	mul.f32 	%f321, %f320, 0f3FB8AA3B;
+	ex2.approx.ftz.f32 	%f322, %f321;
+	add.f32 	%f323, %f316, 0f00000000;
+	ex2.approx.f32 	%f324, %f323;
+	mul.f32 	%f325, %f322, %f324;
+	setp.lt.f32	%p45, %f314, 0fC2D20000;
+	selp.f32	%f326, 0f00000000, %f325, %p45;
+	setp.gt.f32	%p46, %f314, 0f42D20000;
+	selp.f32	%f389, 0f7F800000, %f326, %p46;
+	setp.eq.f32	%p47, %f389, 0f7F800000;
+	@%p47 bra 	BB0_63;
+
+	fma.rn.f32 	%f389, %f389, %f82, %f389;
+
+BB0_63:
+	setp.lt.f32	%p48, %f79, 0f00000000;
+	setp.eq.f32	%p49, %f80, 0f3F800000;
+	and.pred  	%p1, %p48, %p49;
+	mov.b32 	 %r240, %f389;
+	xor.b32  	%r241, %r240, -2147483648;
+	mov.b32 	 %f327, %r241;
+	selp.f32	%f391, %f327, %f389, %p1;
+	setp.eq.f32	%p50, %f79, 0f00000000;
+	@%p50 bra 	BB0_66;
+	bra.uni 	BB0_64;
+
+BB0_66:
+	add.f32 	%f330, %f79, %f79;
+	selp.f32	%f391, %f330, 0f00000000, %p49;
+	bra.uni 	BB0_67;
+
+BB0_64:
+	setp.geu.f32	%p51, %f79, 0f00000000;
+	@%p51 bra 	BB0_67;
+
+	cvt.rzi.f32.f32	%f329, %f301;
+	setp.neu.f32	%p52, %f329, 0f3EE8BA2E;
+	selp.f32	%f391, 0f7FFFFFFF, %f391, %p52;
+
+BB0_67:
+	add.f32 	%f331, %f81, 0f3EE8BA2E;
+	mov.b32 	 %r242, %f331;
+	setp.lt.s32	%p54, %r242, 2139095040;
+	@%p54 bra 	BB0_72;
+
+	setp.gtu.f32	%p55, %f81, 0f7F800000;
+	@%p55 bra 	BB0_71;
+	bra.uni 	BB0_69;
+
+BB0_71:
+	add.f32 	%f391, %f79, 0f3EE8BA2E;
+	bra.uni 	BB0_72;
+
+BB0_69:
+	setp.neu.f32	%p56, %f81, 0f7F800000;
+	@%p56 bra 	BB0_72;
+
+	selp.f32	%f391, 0fFF800000, 0f7F800000, %p1;
+
+BB0_72:
+	mul.f32 	%f332, %f391, 0f437F0000;
+	setp.eq.f32	%p57, %f79, 0f3F800000;
+	selp.f32	%f333, 0f437F0000, %f332, %p57;
+	cvt.rzi.u32.f32	%r243, %f333;
+	cvt.u16.u32	%rs24, %r243;
+	mov.u16 	%rs25, 255;
+	st.v2.u8 	[%rd73], {%rs24, %rs25};
+	ld.global.u32 	%r292, [imageEnabled];
+
+BB0_73:
+	and.b32  	%r244, %r292, 64;
+	setp.eq.s32	%p58, %r244, 0;
+	@%p58 bra 	BB0_83;
+
+	mul.f32 	%f334, %f383, %f383;
+	fma.rn.f32 	%f335, %f384, %f384, %f334;
+	fma.rn.f32 	%f336, %f382, %f382, %f335;
+	sqrt.rn.f32 	%f337, %f336;
+	rcp.rn.f32 	%f338, %f337;
+	mul.f32 	%f339, %f384, %f338;
+	mul.f32 	%f340, %f383, %f338;
+	mul.f32 	%f341, %f382, %f338;
+	cvt.u64.u32	%rd83, %r3;
+	cvt.u64.u32	%rd82, %r2;
+	mov.u64 	%rd86, image_Dir;
+	cvta.global.u64 	%rd81, %rd86;
+	// inline asm
+	call (%rd80), _rt_buffer_get_64, (%rd81, %r95, %r96, %rd82, %rd83, %rd25, %rd25);
+	// inline asm
+	fma.rn.f32 	%f342, %f339, 0f3F000000, 0f3F000000;
+	mul.f32 	%f343, %f342, 0f437F0000;
+	cvt.rzi.u32.f32	%r247, %f343;
+	fma.rn.f32 	%f344, %f340, 0f3F000000, 0f3F000000;
+	mul.f32 	%f345, %f344, 0f437F0000;
+	cvt.rzi.u32.f32	%r248, %f345;
+	fma.rn.f32 	%f346, %f341, 0f3F000000, 0f3F000000;
+	mul.f32 	%f347, %f346, 0f437F0000;
+	cvt.rzi.u32.f32	%r249, %f347;
+	cvt.u16.u32	%rs26, %r249;
+	cvt.u16.u32	%rs27, %r248;
+	cvt.u16.u32	%rs28, %r247;
+	mov.u16 	%rs29, 255;
+	st.v4.u8 	[%rd80], {%rs28, %rs27, %rs26, %rs29};
+
+BB0_83:
+	ret;
+}
+
+